{
  "best_metric": 2.7254714965820312,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.02257591150242691,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.5151823004853824e-05,
      "eval_loss": 4.564711093902588,
      "eval_runtime": 183.5644,
      "eval_samples_per_second": 50.805,
      "eval_steps_per_second": 12.704,
      "step": 1
    },
    {
      "epoch": 0.0004515182300485382,
      "grad_norm": 4.505808353424072,
      "learning_rate": 4.1e-05,
      "loss": 3.6345,
      "step": 10
    },
    {
      "epoch": 0.0009030364600970764,
      "grad_norm": 4.865635395050049,
      "learning_rate": 8.2e-05,
      "loss": 3.4077,
      "step": 20
    },
    {
      "epoch": 0.0013545546901456147,
      "grad_norm": 5.399093151092529,
      "learning_rate": 0.00012299999999999998,
      "loss": 3.212,
      "step": 30
    },
    {
      "epoch": 0.0018060729201941528,
      "grad_norm": 6.037168502807617,
      "learning_rate": 0.000164,
      "loss": 3.2546,
      "step": 40
    },
    {
      "epoch": 0.002257591150242691,
      "grad_norm": 8.842162132263184,
      "learning_rate": 0.000205,
      "loss": 3.2376,
      "step": 50
    },
    {
      "epoch": 0.002257591150242691,
      "eval_loss": 3.3135757446289062,
      "eval_runtime": 185.7849,
      "eval_samples_per_second": 50.198,
      "eval_steps_per_second": 12.552,
      "step": 50
    },
    {
      "epoch": 0.0027091093802912294,
      "grad_norm": 4.627725601196289,
      "learning_rate": 0.00020475031515163197,
      "loss": 3.1244,
      "step": 60
    },
    {
      "epoch": 0.0031606276103397675,
      "grad_norm": 4.629662990570068,
      "learning_rate": 0.00020400247704601096,
      "loss": 3.0593,
      "step": 70
    },
    {
      "epoch": 0.0036121458403883056,
      "grad_norm": 4.690089225769043,
      "learning_rate": 0.00020276012907521508,
      "loss": 2.9041,
      "step": 80
    },
    {
      "epoch": 0.004063664070436844,
      "grad_norm": 5.650446891784668,
      "learning_rate": 0.00020102932383367768,
      "loss": 2.7957,
      "step": 90
    },
    {
      "epoch": 0.004515182300485382,
      "grad_norm": 6.984936237335205,
      "learning_rate": 0.00019881849363055561,
      "loss": 3.173,
      "step": 100
    },
    {
      "epoch": 0.004515182300485382,
      "eval_loss": 3.0686392784118652,
      "eval_runtime": 185.0562,
      "eval_samples_per_second": 50.395,
      "eval_steps_per_second": 12.602,
      "step": 100
    },
    {
      "epoch": 0.004966700530533921,
      "grad_norm": 6.514296531677246,
      "learning_rate": 0.00019613840940836658,
      "loss": 2.8477,
      "step": 110
    },
    {
      "epoch": 0.005418218760582459,
      "grad_norm": 4.205728054046631,
      "learning_rate": 0.00019300212826804002,
      "loss": 2.9135,
      "step": 120
    },
    {
      "epoch": 0.005869736990630997,
      "grad_norm": 3.894537925720215,
      "learning_rate": 0.00018942492985603364,
      "loss": 2.8827,
      "step": 130
    },
    {
      "epoch": 0.006321255220679535,
      "grad_norm": 5.284046173095703,
      "learning_rate": 0.0001854242419234321,
      "loss": 3.052,
      "step": 140
    },
    {
      "epoch": 0.006772773450728073,
      "grad_norm": 5.975098609924316,
      "learning_rate": 0.00018101955541969522,
      "loss": 3.3612,
      "step": 150
    },
    {
      "epoch": 0.006772773450728073,
      "eval_loss": 2.9804024696350098,
      "eval_runtime": 183.7514,
      "eval_samples_per_second": 50.753,
      "eval_steps_per_second": 12.691,
      "step": 150
    },
    {
      "epoch": 0.007224291680776611,
      "grad_norm": 3.6714208126068115,
      "learning_rate": 0.00017623232953471174,
      "loss": 2.7889,
      "step": 160
    },
    {
      "epoch": 0.007675809910825149,
      "grad_norm": 4.271055698394775,
      "learning_rate": 0.00017108588715178296,
      "loss": 2.617,
      "step": 170
    },
    {
      "epoch": 0.008127328140873687,
      "grad_norm": 4.206169128417969,
      "learning_rate": 0.00016560530122087996,
      "loss": 2.8274,
      "step": 180
    },
    {
      "epoch": 0.008578846370922226,
      "grad_norm": 4.710639476776123,
      "learning_rate": 0.00015981727260575154,
      "loss": 3.0149,
      "step": 190
    },
    {
      "epoch": 0.009030364600970764,
      "grad_norm": 6.937736511230469,
      "learning_rate": 0.00015375,
      "loss": 3.3344,
      "step": 200
    },
    {
      "epoch": 0.009030364600970764,
      "eval_loss": 2.9288151264190674,
      "eval_runtime": 184.0887,
      "eval_samples_per_second": 50.66,
      "eval_steps_per_second": 12.668,
      "step": 200
    },
    {
      "epoch": 0.009481882831019302,
      "grad_norm": 2.8257806301116943,
      "learning_rate": 0.00014743304254588043,
      "loss": 2.6591,
      "step": 210
    },
    {
      "epoch": 0.009933401061067841,
      "grad_norm": 3.0818326473236084,
      "learning_rate": 0.000140897175825131,
      "loss": 2.7175,
      "step": 220
    },
    {
      "epoch": 0.010384919291116379,
      "grad_norm": 4.327859878540039,
      "learning_rate": 0.0001341742419234321,
      "loss": 2.657,
      "step": 230
    },
    {
      "epoch": 0.010836437521164918,
      "grad_norm": 5.220002174377441,
      "learning_rate": 0.00012729699429896594,
      "loss": 2.8733,
      "step": 240
    },
    {
      "epoch": 0.011287955751213455,
      "grad_norm": 5.847310543060303,
      "learning_rate": 0.00012029893821086038,
      "loss": 2.9887,
      "step": 250
    },
    {
      "epoch": 0.011287955751213455,
      "eval_loss": 2.8600337505340576,
      "eval_runtime": 183.953,
      "eval_samples_per_second": 50.698,
      "eval_steps_per_second": 12.677,
      "step": 250
    },
    {
      "epoch": 0.011739473981261994,
      "grad_norm": 2.9359610080718994,
      "learning_rate": 0.00011321416748493448,
      "loss": 2.7982,
      "step": 260
    },
    {
      "epoch": 0.012190992211310531,
      "grad_norm": 2.9160430431365967,
      "learning_rate": 0.00010607719841200637,
      "loss": 2.6641,
      "step": 270
    },
    {
      "epoch": 0.01264251044135907,
      "grad_norm": 3.4751181602478027,
      "learning_rate": 9.892280158799368e-05,
      "loss": 2.6787,
      "step": 280
    },
    {
      "epoch": 0.013094028671407609,
      "grad_norm": 4.7677388191223145,
      "learning_rate": 9.178583251506553e-05,
      "loss": 2.9618,
      "step": 290
    },
    {
      "epoch": 0.013545546901456146,
      "grad_norm": 5.446451663970947,
      "learning_rate": 8.470106178913964e-05,
      "loss": 3.2181,
      "step": 300
    },
    {
      "epoch": 0.013545546901456146,
      "eval_loss": 2.802130699157715,
      "eval_runtime": 181.988,
      "eval_samples_per_second": 51.245,
      "eval_steps_per_second": 12.814,
      "step": 300
    },
    {
      "epoch": 0.013997065131504685,
      "grad_norm": 2.6413748264312744,
      "learning_rate": 7.770300570103407e-05,
      "loss": 2.5587,
      "step": 310
    },
    {
      "epoch": 0.014448583361553222,
      "grad_norm": 2.954564094543457,
      "learning_rate": 7.08257580765679e-05,
      "loss": 2.5426,
      "step": 320
    },
    {
      "epoch": 0.014900101591601761,
      "grad_norm": 4.0135931968688965,
      "learning_rate": 6.410282417486901e-05,
      "loss": 2.715,
      "step": 330
    },
    {
      "epoch": 0.015351619821650299,
      "grad_norm": 4.68234395980835,
      "learning_rate": 5.756695745411955e-05,
      "loss": 2.6955,
      "step": 340
    },
    {
      "epoch": 0.015803138051698837,
      "grad_norm": 10.842591285705566,
      "learning_rate": 5.125000000000002e-05,
      "loss": 3.2327,
      "step": 350
    },
    {
      "epoch": 0.015803138051698837,
      "eval_loss": 2.758694648742676,
      "eval_runtime": 188.1269,
      "eval_samples_per_second": 49.573,
      "eval_steps_per_second": 12.396,
      "step": 350
    },
    {
      "epoch": 0.016254656281747375,
      "grad_norm": 3.1886544227600098,
      "learning_rate": 4.518272739424847e-05,
      "loss": 2.5843,
      "step": 360
    },
    {
      "epoch": 0.016706174511795915,
      "grad_norm": 4.394619941711426,
      "learning_rate": 3.9394698779120026e-05,
      "loss": 2.6041,
      "step": 370
    },
    {
      "epoch": 0.017157692741844453,
      "grad_norm": 3.7810781002044678,
      "learning_rate": 3.3914112848217066e-05,
      "loss": 2.6417,
      "step": 380
    },
    {
      "epoch": 0.01760921097189299,
      "grad_norm": 4.610939979553223,
      "learning_rate": 2.8767670465288276e-05,
      "loss": 2.6743,
      "step": 390
    },
    {
      "epoch": 0.018060729201941527,
      "grad_norm": 5.860191345214844,
      "learning_rate": 2.3980444580304764e-05,
      "loss": 3.1479,
      "step": 400
    },
    {
      "epoch": 0.018060729201941527,
      "eval_loss": 2.735464572906494,
      "eval_runtime": 185.0743,
      "eval_samples_per_second": 50.391,
      "eval_steps_per_second": 12.6,
      "step": 400
    },
    {
      "epoch": 0.018512247431990068,
      "grad_norm": 2.952505588531494,
      "learning_rate": 1.9575758076567897e-05,
      "loss": 2.5131,
      "step": 410
    },
    {
      "epoch": 0.018963765662038605,
      "grad_norm": 3.583050012588501,
      "learning_rate": 1.557507014396634e-05,
      "loss": 2.4948,
      "step": 420
    },
    {
      "epoch": 0.019415283892087142,
      "grad_norm": 3.9211292266845703,
      "learning_rate": 1.1997871731959984e-05,
      "loss": 2.6896,
      "step": 430
    },
    {
      "epoch": 0.019866802122135683,
      "grad_norm": 3.595341444015503,
      "learning_rate": 8.861590591633399e-06,
      "loss": 2.6609,
      "step": 440
    },
    {
      "epoch": 0.02031832035218422,
      "grad_norm": 6.866179466247559,
      "learning_rate": 6.181506369444397e-06,
      "loss": 3.1241,
      "step": 450
    },
    {
      "epoch": 0.02031832035218422,
      "eval_loss": 2.7266805171966553,
      "eval_runtime": 186.0159,
      "eval_samples_per_second": 50.135,
      "eval_steps_per_second": 12.537,
      "step": 450
    },
    {
      "epoch": 0.020769838582232757,
      "grad_norm": 3.088073968887329,
      "learning_rate": 3.970676166322313e-06,
      "loss": 2.602,
      "step": 460
    },
    {
      "epoch": 0.021221356812281295,
      "grad_norm": 3.8279261589050293,
      "learning_rate": 2.239870924784917e-06,
      "loss": 2.5787,
      "step": 470
    },
    {
      "epoch": 0.021672875042329835,
      "grad_norm": 4.529348373413086,
      "learning_rate": 9.97522953989038e-07,
      "loss": 2.6237,
      "step": 480
    },
    {
      "epoch": 0.022124393272378372,
      "grad_norm": 4.052964210510254,
      "learning_rate": 2.4968484836801973e-07,
      "loss": 2.7617,
      "step": 490
    },
    {
      "epoch": 0.02257591150242691,
      "grad_norm": 6.235555171966553,
      "learning_rate": 0.0,
      "loss": 2.8884,
      "step": 500
    },
    {
      "epoch": 0.02257591150242691,
      "eval_loss": 2.7254714965820312,
      "eval_runtime": 185.5313,
      "eval_samples_per_second": 50.266,
      "eval_steps_per_second": 12.569,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4510470344540160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}